CN117958965A

CN117958965A - Preoperative path planning method and device for vascular intervention operation

Info

Publication number: CN117958965A
Application number: CN202410121822.9A
Authority: CN
Inventors: 张瑜; 马骏; 郑凌霄; 兰宏志
Original assignee: Shenzhen Raysight Intelligent Medical Technology Co Ltd
Current assignee: Shenzhen Raysight Intelligent Medical Technology Co Ltd
Priority date: 2024-01-29
Filing date: 2024-01-29
Publication date: 2024-05-03

Abstract

The application provides a preoperative path planning method and device for vascular interventional operation, comprising the following steps: acquiring an initial coronary CT contrast image; carrying out three-dimensional reconstruction and plaque quantitative analysis on blood vessels according to the initial coronary artery CT contrast image, and determining an initial coronary artery three-dimensional model and plaque analysis result; correcting the initial coronary artery three-dimensional model according to the plaque analysis result to determine a target coronary artery lumen three-dimensional model; determining functional parameters of each position on the coronary artery according to the three-dimensional model; acquiring instrument parameters of medical instruments used in surgery, and blood vessel attribute parameters and image parameters of a target blood vessel segment; and carrying out path planning processing according to the instrument parameters of the medical instrument, the blood vessel attribute parameters of the target blood vessel section and the image parameters, and determining the travelling path of the medical instrument from the starting point to the ending point. By the technical scheme of automatically planning the path before operation, the application can effectively shorten the operation time and reduce the harm of radiation to patients.

Description

Preoperative path planning method and device for vascular intervention operation

Technical Field

The application relates to the technical field of surgical navigation, in particular to a preoperative path planning method and device for vascular interventional surgery.

Background

The vascular intervention robot is medical equipment for performing vascular intervention operation, integrates high-tech means, has comprehensive performances of operation image guidance, minimally invasive operation and the like, organically combines a robot technology with the vascular intervention operation, and can be matched with a doctor to finish the vascular intervention operation rapidly and accurately. In the vascular intervention operation, a doctor operates a vascular intervention robot, and introduces special precise instruments such as a catheter, a guide wire and the like in the vascular intervention operation into a human body in a man-machine interaction mode to diagnose and locally treat in-vivo pathological conditions.

Current surgical protocols generally include the following two types: 1. when coronary angiography is carried out, a doctor analyzes according to the condition of seeing the stenosis inside the coronary artery, and carries out walking path planning of the guide wire according to the analysis result, and finally, the doctor and the operation robot interactively execute the guide wire feeding scheme; 2. the patient shoots coronary artery CT Contrast (CCTA) before operation, carries out binary pixel reconstruction on the CCTA, acquires some three-dimensional information of lesion blood vessels by reconstructed images, roughly determines the starting point and the end point of a guide wire, and then carries out the determination of the guide wire path by a doctor in the operation process.

However, the above solution has the following drawbacks that the solution 1 directly uses coronary angiography as a reference, and although the resolution is higher than that of CT, it can only provide two-dimensional information, and lacks three-dimensional spatial information; secondly, two-dimensional coronary angiography determines that the blood vessel information is missing, and an experienced doctor is required to analyze and determine the path of the guide wire due to the missing part of the information, so that the burden of the doctor is increased, and the pressure of medical resources is increased; furthermore, the time during PCI surgery is valuable, the patient is suffering from radiation hazards, more complex protocol determinations require longer decision time, increase physician stress, decrease surgical safety, and increase radiation hazards to the patient. The scheme 2 is to build a three-dimensional model (formed by stacking a plurality of small squares) at a pixel level, which is not in accordance with the real shape of a blood vessel, and the deviation from the actual situation is larger even if the preoperative path planning is performed; the establishment of the pixel-level three-dimensional model provides a doctor or a surgical robot with certain three-dimensional space information before operation, but still does not have fine and accurate guide wire path planning.

Disclosure of Invention

Accordingly, the application aims to provide a preoperative path planning method and device for vascular interventional operation, which can automatically plan the path before operation, thereby being capable of being matched with simulated operation before PCI operation and assisting doctors to perform efficient and accurate interaction with an operation robot, effectively shortening PCI operation time, relieving doctor-patient pressure, increasing operation safety and reducing the harm of radiation to patients.

The embodiment of the application provides a preoperative path planning method for vascular interventional operation, which comprises the following steps:

acquiring an initial coronary CT contrast image;

performing three-dimensional reconstruction and plaque quantitative analysis on the blood vessel according to the initial coronary artery CT contrast image, and determining an initial coronary artery three-dimensional model and plaque analysis results;

correcting the initial coronary artery three-dimensional model according to the plaque analysis result to determine a target coronary artery lumen three-dimensional model;

determining functional parameters of each position on the coronary artery according to the three-dimensional model of the target coronary vessel cavity;

Acquiring instrument parameters of medical instruments used in vascular interventional surgery, and vascular attribute parameters and image parameters of a target vascular segment; the target vessel segment is a vessel segment between a starting point and a finishing point determined according to a three-dimensional model of a target coronary vessel cavity, and the attribute parameters comprise morphological parameters and functional parameters of the target vessel segment;

and carrying out path planning processing according to the instrument parameters of the medical instrument, the blood vessel attribute parameters of the target blood vessel section and the image parameters, and determining the travelling path of the medical instrument from the starting point to the ending point.

Optionally, the performing three-dimensional reconstruction of a blood vessel and plaque quantization analysis according to the initial coronary artery CT contrast image, determining an initial coronary artery three-dimensional model includes:

performing image segmentation processing on the initial coronary artery CT contrast image to obtain an initial binary coronary artery tree segmentation result;

Performing coronary tree central line extraction processing on the initial binary coronary tree segmentation result to determine a coronary tree central line;

for each central line point on the central line of the coronary artery tree, carrying out blood vessel contour prediction processing according to the initial coronary artery CT contrast image, and determining the blood vessel contour at the position of each central line point;

and (3) carrying out orderly lofting treatment on the blood vessel contours at all the central line points to obtain an initial coronary three-dimensional model.

Optionally, the plaque analysis result includes at least one of: plaque type, plaque location, plaque size, and degree of lumen narrowing caused by plaque.

Optionally, the determining the functional parameter of each position on the coronary artery according to the three-dimensional model of the target coronary vessel cavity includes:

Inputting the three-dimensional model of the target coronary vessel cavity and the boundary condition of the coronary artery into a hemodynamic simulation model, and determining functional parameters of each position on the coronary artery; the boundary condition of the coronary artery is determined according to the blood flow velocity in the coronary artery and the pre-acquired aortic pressure, and the blood flow velocity in the coronary artery is determined according to the three-dimensional model of the target coronary vessel cavity.

Optionally, after determining the functional parameter of each position on the coronary artery according to the three-dimensional model of the target coronary vessel cavity, the preoperative path planning method further comprises:

And filling corresponding colors in all positions of the three-dimensional model of the target coronary vessel cavity according to blood flow reserve fractions in functional parameters of all positions on the coronary artery, and displaying the three-dimensional model of the target coronary vessel cavity after filling the colors on an interactive interface.

Optionally, the path planning process is performed according to the instrument parameter of the medical instrument and the blood vessel attribute parameter and the image parameter of the target blood vessel segment, and the determining the travel path of the medical instrument from the starting point to the ending point includes:

Determining a path key point from a starting point to a finishing point by utilizing a pre-trained key point extraction model based on instrument parameters of the medical instrument, blood vessel attribute parameters of a target blood vessel section and image parameters;

And performing curve fitting processing according to the starting point, the ending point, the path key points and the morphological parameters of the target vessel segment to determine the advancing path.

Optionally, the determining the path key point from the starting point to the end point by using a pre-trained key point extraction model based on the instrument parameter of the medical instrument and the blood vessel attribute parameter and the image parameter of the target blood vessel segment includes:

Constructing a first feature vector according to the vessel attribute parameters of the target vessel segment;

constructing a second feature vector according to the instrument parameters of the medical instrument;

Constructing a three-dimensional feature matrix according to the image information of the target vessel segment;

and inputting the fused first feature vector, second feature vector and three-dimensional feature matrix into a key point extraction model, and determining the path key points from the starting point to the end point.

The embodiment of the application also provides a preoperative path planning device for vascular interventional operation, which comprises:

The first acquisition module is used for acquiring an initial coronary CT contrast image;

The first determining module is used for carrying out three-dimensional reconstruction of blood vessels and plaque quantitative analysis according to the initial coronary artery CT contrast image, and determining an initial coronary artery three-dimensional model and plaque analysis results;

the second determining module is used for correcting the initial coronary artery three-dimensional model according to the plaque analysis result to determine a target coronary artery cavity three-dimensional model;

the third determining module is used for determining functional parameters of each position on the coronary artery according to the three-dimensional model of the target coronary vessel cavity;

the second acquisition module is used for acquiring instrument parameters of medical instruments used in vascular interventional operation, and vascular attribute parameters and image parameters of a target vascular segment; the target vessel segment is a vessel segment between a starting point and a finishing point determined according to a three-dimensional model of a target coronary vessel cavity, and the attribute parameters comprise morphological parameters and functional parameters of the target vessel segment;

And the path planning module is used for carrying out path planning processing according to the instrument parameters of the medical instrument, the blood vessel attribute parameters of the target blood vessel section and the image parameters and determining the travelling path of the medical instrument from the starting point to the ending point.

Optionally, when the first determining module is configured to perform three-dimensional reconstruction of a blood vessel and plaque quantization analysis according to the initial coronary CT contrast image, determine an initial coronary three-dimensional model, the first determining module is configured to:

Optionally, the third determining module is configured to, when configured to determine the functional parameter of each position on the coronary artery according to the three-dimensional model of the target coronary vessel lumen,:

Optionally, the preoperative path planning device is further configured to:

Optionally, when the path planning module is configured to perform path planning processing according to the instrument parameter of the medical instrument and the blood vessel attribute parameter and the image parameter of the target blood vessel segment, the path planning module is configured to:

Optionally, when the path planning module is configured to determine a path key point between a start point and an end point by using a pre-trained key point extraction model based on an instrument parameter of the medical instrument and a blood vessel attribute parameter and an image parameter of a target blood vessel segment, the path planning module is configured to:

The embodiment of the application also provides electronic equipment, which comprises: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of preoperative path planning as described above.

Embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a pre-operative path planning method as described above.

The embodiment of the application provides a preoperative path planning method and device for vascular interventional operation, comprising the following steps: acquiring an initial coronary CT contrast image; performing three-dimensional reconstruction and plaque quantitative analysis on the blood vessel according to the initial coronary artery CT contrast image, and determining an initial coronary artery three-dimensional model and plaque analysis results; correcting the initial coronary artery three-dimensional model according to the plaque analysis result to determine a target coronary artery lumen three-dimensional model; determining functional parameters of each position on the coronary artery according to the three-dimensional model of the target coronary vessel cavity; acquiring instrument parameters of medical instruments used in vascular interventional surgery, and vascular attribute parameters and image parameters of a target vascular segment; the target vessel segment is a vessel segment between a starting point and a finishing point determined according to a three-dimensional model of a target coronary vessel cavity, and the attribute parameters comprise morphological parameters and functional parameters of the target vessel segment; and carrying out path planning processing according to the instrument parameters of the medical instrument, the blood vessel attribute parameters of the target blood vessel section and the image parameters, and determining the travelling path of the medical instrument from the starting point to the ending point.

Thus, the scheme is used for establishing a three-dimensional blood vessel model based on the coronary artery CT contrast image, and gives a realistic three-dimensional blood vessel model, quantitative display of plaques and display of functional calculation results before operation, thereby effectively assisting doctors in making scheme decisions before operation; after the starting point and the end point are determined, the scheme can automatically perform path simulation, and the optimal travelling path is obtained in a combined way so as to avoid some important positions, and finally the whole preoperative path planning closed loop is completed.

The preoperative path planning method for the vascular interventional operation has the advantages that:

1) The automatic path planning before operation in the scheme can greatly reduce decision time in PCI operation, strives for precious operation time for patients and doctors, and greatly reduces the burden of the doctors and the radiation hazard of the patients.

2) According to the automatic path planning method and device, a doctor or a surgical robot can be assisted to conduct path implementation to a large extent, so that a doctor with a slightly shallow experience can be more confident in operating the surgical robot, and the doctor and a patient can be helped to finish surgery smoothly.

3) The three-dimensional reconstruction method adopted by the scheme can restore the real situation of the blood vessel to the greatest extent, comprises quantitative information display of lesion positions such as similar circular lumens, plaques and the like, and calculation results of the functions, and provides omnibearing morphological and functional information for reference before and during operation of doctors or operation robots.

In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a method for planning a preoperative path of a vascular interventional procedure according to an embodiment of the present application;

FIG. 2 provides a schematic representation of a binary coronary tree segmentation result based on deep learning as a framework;

FIG. 3 is a schematic diagram of determining a coronary tree centerline based on deep learning in accordance with the present application;

FIG. 4 is a schematic diagram of predicting a vessel contour based on deep learning according to the present application;

FIG. 5 is a schematic diagram of the structure of an initial three-dimensional model of coronary artery determined after lofting according to the present application;

FIG. 6 is a schematic diagram of a three-dimensional model of a target coronary vessel cavity provided by the application;

FIG. 7 is a schematic diagram of a functional parameter for determining each location on a coronary artery according to the present application;

FIG. 8 is a schematic illustration of a pre-operative planned path of travel provided by the present application;

FIG. 9 is a schematic diagram of a determination of a pre-operative planned path of travel provided by the present application;

fig. 10 is a schematic structural diagram of a preoperative path planning device for vascular intervention according to an embodiment of the present application;

Fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. Based on the embodiments of the present application, every other embodiment obtained by a person skilled in the art without making any inventive effort falls within the scope of protection of the present application.

Based on the above, the embodiment of the application provides a preoperative path planning method and device for vascular interventional operation, which can automatically plan the path before operation, thereby being capable of being matched with the simulation operation before PCI operation and assisting doctors to carry out high-efficiency and accurate interaction with an operation robot so as to effectively shorten the PCI operation time, reduce the doctor-patient pressure, increase the operation safety and reduce the harm of radiation to patients.

Referring to fig. 1, fig. 1 is a flowchart of a method for planning a preoperative path of a vascular intervention according to an embodiment of the present application.

This is, in particular, a Percutaneous Coronary Intervention (PCI) procedure. Percutaneous coronary intervention (percutaneous coronary intervention, PCI) refers to a treatment method that uses cardiac catheter techniques to open the lumen of a stenosed or even occluded coronary artery, thereby improving the perfusion of the blood flow to the myocardium. It is common to employ the femoral or radial approach to deliver the guide catheter to the coronary ostium to be dilated, and then deliver the balloon or stent of the corresponding size along the guidewire to the stenosed segment for dilation with appropriate pressure and time to achieve the purpose of restenosis relief based on the characteristics of the lesion.

As shown in fig. 1, the method for planning a preoperative path provided by the embodiment of the present application includes:

S101, acquiring an initial coronary artery CT contrast image.

In the step, an initial coronary artery CT contrast image shot before the operation of a target patient is acquired; the initial coronary CT contrast image is a three-dimensional contrast image.

The coronary artery CT contrast image is also called CCTA, and is a three-dimensional image obtained by scanning a coronary artery by a plurality of spiral CT lines after intravenous injection of an appropriate contrast agent.

And S102, carrying out three-dimensional reconstruction and plaque quantitative analysis on the blood vessel according to the initial coronary artery CT contrast image, and determining an initial coronary artery three-dimensional model and plaque analysis result.

In the step, three-dimensional reconstruction of blood vessels is carried out according to the initial coronary artery CT contrast image, and an initial coronary artery three-dimensional model is determined; and simultaneously carrying out plaque quantitative analysis according to the initial coronary artery CT contrast image to determine plaque analysis results.

In one embodiment of the present application, the performing three-dimensional reconstruction of a blood vessel and plaque quantization analysis according to the initial coronary CT contrast image, determining an initial coronary three-dimensional model includes:

S1021, performing image segmentation processing on the initial coronary artery CT contrast image to obtain an initial binary coronary artery tree segmentation result.

S1022, carrying out coronary artery tree central line extraction processing on the initial binary coronary artery tree segmentation result, and determining the coronary artery tree central line.

S1023, aiming at each central line point on the central line of the coronary artery tree, carrying out blood vessel contour prediction processing according to the initial coronary artery CT contrast image, and determining the blood vessel contour at the position of each central line point.

S1024, carrying out orderly lofting treatment on the blood vessel contours at all the central line point positions to obtain an initial coronary three-dimensional model.

In step S1021, image segmentation processing is performed on the coronary arteries included in the initial coronary artery CT contrast image, so as to obtain an initial binary coronary artery tree segmentation result.

The initial binary coronary tree segmentation results are pixel-level binary images.

Here, in performing image segmentation, image segmentation includes, but is not limited to, performing image segmentation according to machine learning (support vector machine, random forest, deep learning, etc.), or using a conventional image segmentation algorithm (threshold segmentation, level set, active contour model, etc.).

For example, referring to fig. 2, fig. 2 provides a schematic diagram of a binary coronary tree segmentation result based on deep learning as a framework. Here, first, a plurality of CCTA original images and artificially marked coronary regions are input into a deep neural network for learning, weights of the network are continuously adjusted, and after convergence, the deep learning neural network capable of accurately performing binary coronary tree segmentation is obtained. When the method is used, the output of the CCTA after passing through the network is more and more similar to the manually marked binary segmentation map. As shown in FIG. 2, the rightmost image is the initial binary coronary tree segmentation result.

For step S1022, where the coronary tree centerline extraction process is performed on the initial binary coronary tree segmentation result, the method includes, but is not limited to, some conventional image processing algorithms (such as skeletonizing, frangi feature matrices, etc.), and machine learning-based methods (such as predicting centerline trend and position region by region).

For example, referring to fig. 3, fig. 3 is a schematic diagram illustrating determining a coronary tree centerline based on deep learning according to the present application. Firstly, inputting a large number of examples of binary coronary artery tree segmentation results and manually marked central lines thereof into a central line extraction network for training, and obtaining a neural network capable of extracting the coronary artery central lines after convergence. When the coronary artery tree central line structure is used, the network can return to the central line position and trend of each region, and the central lines of all the regions are connected together to obtain the central line structure of the whole coronary artery tree. As shown in FIG. 3, the rightmost image is the coronary tree centerline.

In step S1023, according to the vessel trend, for each centerline point on the centerline of the coronary tree, vessel contour prediction processing is performed according to the initial coronary CT contrast image, so as to determine the vessel contour at each centerline point. The vessel profile may in particular be a vessel lumen profile.

Here, in performing the vessel contour prediction, methods include, but are not limited to, conventional image processing algorithms, machine learning-based methods (e.g., determining diameters of several angles on each section along a centerline, concatenated into a circular-like contour), etc.

For example, please refer to fig. 4, fig. 4 is a schematic diagram of predicting a blood vessel contour based on deep learning according to the present application. Firstly, after training big data, inputting a lumen section, predicting the radiuses of a plurality of angles of each azimuth, and connecting the outer end points of the radiuses to form a contour.

For step S1024, the initial coronary three-dimensional model is an initial coronary vessel cavity three-dimensional model.

For example, referring to fig. 5, fig. 5 is a schematic structural diagram of an initial three-dimensional model of coronary artery determined after lofting according to the present application.

In one embodiment provided by the present application, the plaque assay results include at least one of: plaque type, plaque location, plaque size, and degree of lumen narrowing caused by plaque.

The plaque position can be obtained by dividing the plaque from the lumen in an image dividing mode, marking the plaque, or positioning the plaque position by adopting a target detection method; the plaque types can be distinguished by a threshold method according to the positioning result, or the plaque types can be obtained by performing feature classification in a feature analysis mode.

In addition, the length of the blood vessel occupied by the stenosis and the reference caliber of the normal blood vessel can be included.

S103, correcting the initial coronary artery three-dimensional model according to the plaque analysis result, and determining a target coronary artery cavity three-dimensional model.

In the step, the plaque analysis result determined by coronary artery analysis is combined with the initial coronary artery three-dimensional model so as to achieve the purpose of correcting the initial coronary artery three-dimensional model, and then the combined three-dimensional model is determined to be a target coronary artery cavity three-dimensional model.

Here, the target coronary vessel lumen three-dimensional model is a model with plaque information indications.

For example, referring to fig. 6, fig. 6 is a schematic structural diagram of a three-dimensional model of a target coronary vessel cavity according to the present application.

S104, determining functional parameters of each position on the coronary artery according to the three-dimensional model of the target coronary vessel cavity.

Here, the functional parameters include, but are not limited to, fractional flow reserve and microcirculation resistance index.

In one embodiment of the present application, the determining the functional parameter of each position on the coronary artery according to the three-dimensional model of the target coronary vessel cavity includes: inputting the three-dimensional model of the target coronary vessel cavity and the boundary condition of the coronary artery into a hemodynamic simulation model, and determining the functional parameters of each position on the coronary artery.

Here, the boundary condition of the coronary is determined from the blood flow velocity in the coronary, which is determined from the three-dimensional model of the target coronary vessel lumen, and the pre-acquired aortic pressure.

And the aortic pressure is obtained from the vascular pressure of the target patient, and the vascular pressure is correspondingly processed to obtain the aortic pressure of the target patient.

The boundary conditions include inlet flow boundary conditions, outlet resistance boundary conditions, and the like.

For example, referring to fig. 7, fig. 7 is a schematic diagram of a functional parameter for determining each position on a coronary artery according to the present application. As shown in fig. 7, there is shown a process for determining fractional flow reserve from a three-dimensional model of a target coronary lumen.

In one embodiment of the present application, after determining the functional parameters of each location on the coronary artery according to the three-dimensional model of the target coronary vessel lumen, the pre-operative path planning method further includes: and filling corresponding colors in all positions of the three-dimensional model of the target coronary vessel cavity according to blood flow reserve fractions in functional parameters of all positions on the coronary artery, and displaying the three-dimensional model of the target coronary vessel cavity after filling the colors on an interactive interface.

Here, the interactive interface may be an interface presented for viewing by a target person.

Wherein the blood supply at each location on the coronary artery can be characterized by color filling.

S105, acquiring instrument parameters of medical instruments used in vascular interventional operations, and vascular attribute parameters and image parameters of a target vascular segment.

Here, the target vessel segment is a vessel segment between a start point and an end point determined from the three-dimensional model of the target coronary vessel lumen, and the attribute parameters include morphological parameters and functional parameters of the target vessel segment.

The starting point and the ending point can be selected by relevant professionals according to the three-dimensional model of the target coronary vessel cavity, and can also be determined according to depth learning and combining plaque information in the three-dimensional model of the target coronary vessel cavity.

Morphological parameters of the target vessel segment include, but are not limited to, vessel length, lumen size, plaque type, plaque location, stenosis information.

Functional parameters of the target vessel segment include, but are not limited to, fractional flow reserve.

The image parameters of the target vessel segment include, but are not limited to, gray scale values for each pixel.

Including but not limited to guidewires and catheters.

The instrument parameters of the medical instrument include, but are not limited to, hardness, diameter, strength, flexibility, rigidity, and the like.

S106, performing path planning processing according to the instrument parameters of the medical instrument, the blood vessel attribute parameters of the target blood vessel segment and the image parameters, and determining the travel path of the medical instrument from the starting point to the ending point.

Here, the travel path of the medical instrument is a path planned before operation.

Where the pre-operative path planning is performed, numerical processing methods including, but not limited to, spline interpolation (through each known point), and machine learning based curve regression methods (e.g., regression of the path of travel of the medical device along the lumen, and including the position and direction of each key point) are included.

For example, referring to fig. 8, fig. 8 is a schematic diagram of a travel path planned before operation according to the present application. As shown in fig. 8, the pre-operatively planned travel path may be displayed on the target coronary vessel lumen three-dimensional model.

In one embodiment of the present application, the performing a path planning process according to the instrument parameter of the medical instrument and the blood vessel attribute parameter and the image parameter of the target blood vessel segment, and determining the travel path of the medical instrument from the starting point to the ending point includes:

S1061, determining a path key point from a starting point to a finishing point by using a pre-trained key point extraction model based on instrument parameters of the medical instrument, blood vessel attribute parameters of a target blood vessel segment and image parameters;

s1062, performing curve fitting processing according to the starting point, the ending point, the path key points and the morphological parameters of the target vessel segment, and determining the travel path.

In step S1061, in one embodiment of the present application, determining the path key point between the start point and the end point by using a pre-trained key point extraction model based on the instrument parameter of the medical instrument and the blood vessel attribute parameter and the image parameter of the target blood vessel segment includes:

s10611, constructing a first feature vector according to the blood vessel attribute parameters of the target blood vessel segment.

S10612, constructing a second feature vector according to the instrument parameters of the medical instrument.

S10613, constructing a three-dimensional feature matrix according to the image information of the target vessel segment.

S10614, inputting the first feature vector, the second feature vector and the three-dimensional feature matrix into a key point extraction model after fusing, and determining the path key points from the starting point to the end point.

For step S10611, specifically, a first feature vector may be constructed according to the vessel morphology and functional information of the target vessel segment, where elements in the first feature vector may be expressed as whether there is a stenosis/stenosis degree/plaque type/diameter of the stenosis/lumen reference diameter/CT-FFR functional evaluation index, and the elements form a one-dimensional vector.

For step S10612, specifically, a second feature vector may be constructed from the obtained physical information in the instrument parameters of the guide wire or catheter, where the elements in the second feature vector may be represented as physical information of materials such as hardness/diameter/strength/flexibility/rigidity of the guide wire or catheter, and these elements form a one-dimensional vector.

For step S10613, the image information may be a two-dimensional section or a three-dimensional image block, so as to form a three-dimensional feature matrix, which includes gray values of each pixel, and reflects information such as visual shape and texture of the coronary artery, so that feature extraction is facilitated by the neural network.

For step S10614, the above three features are fused, and a vector/matrix addition method or expansion stacking method may be adopted, and the fused three features are input into a neural network to output positions of multiple path key points.

The nature of the neural network is weight parameters which are continuously adjusted in the training process to adapt to the characteristics of input data, such as larger hardness of an input guide wire, larger bending cannot occur during operation, and output key points corresponding to the neural network are relatively close to a fitting curve; on the contrary, if the guide wire has high flexibility, an S-shaped walking position is easy to form in a blood vessel, so that the key point is greatly deviated at the moment, and the relative curvature of the generated path is also larger.

The travel path determined here is a route inside the target vessel segment for step S1062.

In addition, the travel path is determined according to the starting point, the ending point, the path key points and the morphological parameters of the target blood vessel segment, and an interpolation processing mode can be adopted besides curve fitting processing.

Fitting does not require the equation to pass through all known points, and is a look-ahead, i.e., the overall trend is consistent. Interpolation is similar, every known point must pass through, but higher order can occur with the Dragon-Gerdostat phenomenon, so piecewise interpolation is generally used.

For example, referring to fig. 9, fig. 9 is a schematic diagram illustrating a determination process of a pre-operative planned travel path according to the present application. As shown in fig. 9, the keypoint prediction network may be a deep learning network.

Referring to fig. 10, fig. 10 is a schematic structural diagram of a preoperative path planning apparatus for vascular intervention according to an embodiment of the present application. As shown in fig. 10, the preoperative path planning apparatus 200 includes:

a first acquisition module 210 for acquiring an initial coronary CT contrast image;

the first determining module 220 is configured to perform three-dimensional reconstruction of a blood vessel and plaque quantization analysis according to the initial coronary artery CT contrast image, and determine an initial coronary artery three-dimensional model and plaque analysis result;

A second determining module 230, configured to correct the initial coronary artery three-dimensional model according to the plaque analysis result, and determine a target coronary artery lumen three-dimensional model;

A third determining module 240, configured to determine functional parameters of each position on the coronary artery according to the three-dimensional model of the target coronary vessel lumen;

A second obtaining module 250, configured to obtain an instrument parameter of a medical instrument used in the vascular interventional procedure, and a vascular attribute parameter and an image parameter of a target vessel segment; the target vessel segment is a vessel segment between a starting point and a finishing point determined according to a three-dimensional model of a target coronary vessel cavity, and the attribute parameters comprise morphological parameters and functional parameters of the target vessel segment;

The path planning module 260 is configured to perform path planning processing according to the instrument parameters of the medical instrument and the blood vessel attribute parameters and the image parameters of the target blood vessel segment, and determine a travel path of the medical instrument from the starting point to the ending point.

Optionally, when the first determining module 220 is configured to perform three-dimensional reconstruction of a blood vessel and plaque quantization analysis according to the initial coronary CT contrast image, the first determining module 220 is configured to:

Optionally, when the third determining module 240 is configured to determine the functional parameter of each location on the coronary artery according to the three-dimensional model of the target coronary vessel lumen, the third determining module 240 is configured to:

Optionally, the preoperative path planning device 200 is further configured to:

Optionally, when the path planning module 260 is configured to perform a path planning process according to the instrument parameter of the medical instrument and the blood vessel attribute parameter and the image parameter of the target blood vessel segment, the path planning module 260 is configured to:

Optionally, when the path planning module 260 is configured to determine a path keypoint between a start point and an end point based on the instrument parameter of the medical instrument and the vessel attribute parameter and the image parameter of the target vessel segment by using a pre-trained keypoint extraction model, the path planning module 260 is configured to:

Referring to fig. 11, fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the application. As shown in fig. 11, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.

The memory 520 stores machine-readable instructions executable by the processor 510, and when the electronic device 500 is running, the processor 510 communicates with the memory 520 through the bus 530, and when the machine-readable instructions are executed by the processor 510, the steps in the method embodiments shown in fig. 1 to 9 can be executed, and the specific implementation can be referred to the method embodiments, which are not repeated herein.

The embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program may execute the steps in the method embodiments shown in the foregoing fig. 1 to fig. 9 when the computer program is executed by a processor, and a specific implementation manner may refer to the method embodiments and is not repeated herein.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Finally, it should be noted that: the above examples are only specific embodiments of the present application, and are not intended to limit the scope of the present application, but it should be understood by those skilled in the art that the present application is not limited thereto, and that the present application is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. A method for planning a preoperative path of a vascular interventional procedure, the method comprising:

acquiring an initial coronary CT contrast image;

2. The method of claim 1, wherein said performing a three-dimensional reconstruction of blood vessels and plaque quantization from said initial coronary CT contrast image to determine an initial coronary three-dimensional model comprises:

3. The preoperative path planning method of claim 1, wherein the plaque analysis results comprise at least one of: plaque type, plaque location, plaque size, and degree of lumen narrowing caused by plaque.

4. The method of claim 1, wherein determining functional parameters for each location on the coronary artery based on the three-dimensional model of the target coronary vessel lumen comprises:

5. The method of claim 1, wherein after determining functional parameters for each location on the coronary artery from the three-dimensional model of the target coronary vessel lumen, the method further comprises:

6. The method according to claim 1, wherein the step of performing a path planning process based on the instrument parameter of the medical instrument and the blood vessel attribute parameter and the image parameter of the target blood vessel segment to determine the travel path of the medical instrument from the start point to the end point comprises:

7. The method according to claim 6, wherein determining the path keypoints between the start point and the end point based on the instrument parameters of the medical instrument and the vessel attribute parameters and the image parameters of the target vessel segment by using a pre-trained keypoint extraction model comprises:

8. A preoperative path planning apparatus for vascular interventional procedures, the preoperative path planning apparatus comprising:

9. An electronic device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating via said bus when the electronic device is running, said machine readable instructions when executed by said processor performing the steps of the pre-operative path planning method according to any one of claims 1 to 7.

10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the pre-operative path planning method according to any one of claims 1 to 7.